MGKAN: Predicting Asymmetric Drug-Drug Interactions via a Multimodal Graph Kolmogorov-Arnold Network

TL;DR

MGKAN introduces a novel graph neural network with learnable basis functions and multiple network views to improve asymmetric drug-drug interaction prediction, outperforming existing models on benchmark datasets.

Contribution

The paper presents MGKAN, a new GNN model that incorporates learnable basis functions and multiple network views for better modeling of asymmetric DDIs.

Findings

Outperforms seven state-of-the-art baselines.

Effectively captures nonlinear and directional drug interactions.

Demonstrates high predictive accuracy through ablation and case studies.

Abstract

Predicting drug-drug interactions (DDIs) is essential for safe pharmacological treatments. Previous graph neural network (GNN) models leverage molecular structures and interaction networks but mostly rely on linear aggregation and symmetric assumptions, limiting their ability to capture nonlinear and heterogeneous patterns. We propose MGKAN, a Graph Kolmogorov-Arnold Network that introduces learnable basis functions into asymmetric DDI prediction. MGKAN replaces conventional MLP transformations with KAN-driven basis functions, enabling more expressive and nonlinear modeling of drug relationships. To capture pharmacological dependencies, MGKAN integrates three network views-an asymmetric DDI network, a co-interaction network, and a biochemical similarity network-with role-specific embeddings to preserve directional semantics. A fusion module combines linear attention and nonlinear transformation to enhance representational capacity. On two benchmark datasets, MGKAN outperforms seven state-of-the-art baselines. Ablation studies and case studies confirm its predictive accuracy and effectiveness in modeling directional drug effects.